Structured data (JSON-LD) audit

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavior beyond that: it validates required/recommended properties, flags invalid JSON and dates, and checks entity consistency across pages. It also clarifies the sampling approach. No contradictions found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph that front-loads the main action (extract JSON-LD and validate) and then details specific checks and input methods. It is information-dense without being redundant, though it lists many schema types which could be trimmed without losing core meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main functionality, input methods, and validation scope. It does not describe the output format (no output schema exists) or mention limits like maxItems, but those are in the input schema. Given the tool's complexity and the annotations covering safety, the description is reasonably complete for an agent to understand what the tool does and how to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only sitemapUrl has a description). The description explains that urls and sitemapUrl are alternative input methods ('Pass explicit urls or a sitemap'), which adds meaning to those parameters. However, sampleSize is not explicitly described, though 'sample' implies its purpose. The description partially compensates for the low coverage but could be more explicit about sampleSize and the relationship between urls and sitemapUrl.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool extracts JSON-LD from pages, validates properties per schema type, flags invalid JSON/dates, and checks entity consistency. It lists specific schema types and mentions input methods. This distinguishes it from siblings like schema_validate (likely single-schema validation) and eeat_audit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains how to invoke the tool ('Pass explicit urls or a sitemap to sample') but does not explicitly state when to choose this over alternative tools like schema_validate or site_crawl. The intended context is implied by the description but not spelled out with exclusions or comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.